Identifying Respiratory Findings in Emergency Department Reports for Biosurveillance.pdf

MEDINFO 2004 M. Fieschi et al. (Eds) Amsterdam: IOS Press ? 2004 IMIA. All rights reservedIdentifying Respiratory Findings in Emergency Department Reports for Biosurveillance using MetaMap Wendy W Chapmana, Marcelo Fiszmanb, John N Dowlinga, Brian E Chapmanc, Thomas C Rindfleschb a RODS Laboratory, Center for Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA b National Library of Medicine, Bethesda, MD, USA c Department of Radiology, University of Pittsburgh, Pittsburgh, PA, USA Wendy W Chapman, Marcelo Fiszman, John N Dowling, Brian E Chapman, Thomas C RindfleschAbstract Clinical conditions described in patients’ dictated reports are necessary for automated detection of patients with respiratory illnesses such as inhalational anthrax and pneumonia. We ap- plied MetaMap to emergency department reports to extract a set of 71 clinical conditions relevant to detection of a lower respira- tory outbreak. We indexed UMLS terms in emergency depart- ment reports with MetaMap, filtered the indexed output with a specialized lexicon of UMLS terms for the domain, and mapped the clinical conditions of interest to concepts in the lexicon. We compared MetaMap’s ability to accurately identify the condi- tions against a physician’s manual annotations and evaluated incorrectly indexed features to determine what additional pro- cessing is necessary. MetaMap identified the clinical conditions with a recall of 0.72 and a precision of 0.56. Necessary processing beyond MetaMap’s indexing includes finding validation, temporal dis- crimination, anatomic location discrimination, finding-disease discrimination, and contextual inference. Successful identifica- tion of clinical conditions in an emergency department report with MetaMap requires processing techniques specific to the clinical question of interest. Keywords: Natural Language Processing, Information Extraction, Biosur- veillance, Disease Outbreaks Introduction The recent Severe Acute Respiratory Syn